AV
Andrea Vedaldi
cs.CVcs.LGcs.AIcs.GRstat.MLcs.NEeess.AScs.ROConvolutional neural networkscs.SD
On Valency
published · living versionsW_mv8ghxt6·v1 · currentpublished
OverSeer: Multi-Agent World Models Beyond What Agents See
with Runjia Li, Kam Woh Ng, Minghao Chen, Junlin Han +4
1 version
W_dr6njmxz·v1published
Preprints & journals
227 papers in the corpus · 2012–2026OverSeer: Multi-Agent World Models Beyond What Agents See2610.28554v1 · Runjia Li, Kam Woh Ng, Minghao Chen et al.2026 · 0 citationsarXivon Valency
Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion2610.25276v1 · Yushi Lan, Zeren Jiang, Koichi Namekata et al.2026 · 0 citationsarXiv
JtT: Rethinking Point Trajectory Diffusion for Diverse and Rigid Motion from an Image2610.16591v1 · Gabrijel Boduljak, Yushi Lan, Christian Rupprecht et al.2026 · 0 citationsarXiv
Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark2610.13947v3 · Xudong Cai, Ruijie Zhu, Haoliang Shang et al.2026 · 0 citationsarXiv
SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion2607.05392v1 · Paul Engstler, Iro Laina, Christian Rupprecht et al.2026 · 0 citationsarXiv
PhysiFormer: Learning to Simulate Mechanics in World Space2606.27364v1 · Yiming Chen, Yushi Lan, Andrea Vedaldi2026 · 0 citationsarXiv
Go-with-the-Track: Video Compositing and Motion Control with Point Tracking2606.20891v1 · Koichi Namekata, Yash Kant, Zhizheng Liu et al.2026 · 0 citationsarXiv
Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control2606.14699v1 · Ruining Li, Yuxin Yao, Matt Zhou et al.2026 · 0 citationsarXiv
MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer2606.04621v2 · Weiyu Li, Antoine Toisoul, Tom Monnier et al.2026 · 0 citationsarXiv
AssetGen: Deployable 3D Asset Generation at Interactive Speed2605.26137v1 · Dilin Wang, Xiaoyu Xiang, Kihyuk Sohn et al.2026 · 0 citationsarXiv
Articraft: An Agentic System for Scalable Articulated 3D Asset Generation2605.15187v1 · Matt Zhou, Ruining Li, Xiaoyang Lyu et al.2026 · 0 citationsarXiv
VGGT-2605.15195v2 · Jianyuan Wang, Minghao Chen, Shangzhan Zhang et al.2026 · 0 citationsarXiv
Syn4D: A Multiview Synthetic 4D Dataset2605.05207v2 · Zeren Jiang, Yushi Lan, Yihang Luo et al.2026 · 0 citationsarXiv
MeshReGen: A Unified 3D Geometry Regeneration Framework2604.28134v2 · Geon Yeong Park, Roman Shapovalov, Rakesh Ranjan et al.2026 · 0 citationsarXiv
Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction2604.04874v1 · Ahan Shabanov, Peter Hedman, Ethan Weber et al.2026 · 0 citationsarXiv
Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning2605.13852v1 · Ido Sobol, Kihyuk Sohn, Yoav Blum et al.2026 · 0 citationsarXiv
LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis2603.20176v3 · Stanislaw Szymanowicz, Minghao Chen, Jianyuan Wang et al.2026 · 0 citationsarXiv
NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction2603.04179v2 · Weirong Chen, Chuanxia Zheng, Ganlin Zhang et al.2026 · 0 citationsarXiv
CoWTracker: Tracking by Warping instead of Correlation2602.04877v1 · Zihang Lai, Eldar Insafutdinov, Edgar Sucar et al.2026 · 0 citationsarXiv
LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models2601.14674v2 · Mingyang Xie, Numair Khan, Tianfu Wang et al.2026 · 0 citationsarXiv
V-DPM: 4D Video Reconstruction with Dynamic Point Maps2601.09499v1 · Edgar Sucar, Eldar Insafutdinov, Zihang Lai et al.2026 · 0 citationsarXiv
Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video2601.05251v1 · Zeren Jiang, Chuanxia Zheng, Iro Laina et al.2026 · 0 citationsarXiv
WorldGen: From Text to Traversable and Interactive 3D Worlds2511.16825v1 · Dilin Wang, Hyunyoung Jung, Tom Monnier et al.2025 · 0 citationsarXiv
What Happens Next? Anticipating Future Motion by Generating Point Trajectories2509.21592v2 · Gabrijel Boduljak, Laurynas Karazija, Iro Laina et al.2025 · 0 citationsICLR 2026
DINOv32508.10104v1 · Oriane Sim'eoni, Huy V. Vo, Maximilian Seitzer et al.2025 · 41 citationsarXiv
Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey2507.14501v5 · Jiahui Zhang, Yuelei Li, Anpei Chen et al.2025 · 4 citationsarXiv
AutoPartGen: Autogressive 3D Part Generation and Discovery2507.13346v2 · Minghao Chen, Jianyuan Wang, Roman Shapovalov et al.2025 · 0 citationsarXiv
VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory2506.18903v3 · Runjia Li, Philip Torr, Andrea Vedaldi et al.2025 · 12 citationsarXiv
Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos2506.05546v2 · Vadim Tschernezki, Diane Larlus, Iro Laina et al.2025 · 0 citationsarXiv
Triangle Splatting for Real-Time Radiance Field Rendering2505.19175v1 · Jan Held, Renaud Vandeghen, Adrien Deliege et al.2025 · 8 citationsarXiv
Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction2504.14516v2 · Weirong Chen, Ganlin Zhang, Felix Wimbauer et al.2025 · 1 citationarXiv
Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction2504.07961v2 · Zeren Jiang, Chuanxia Zheng, Iro Laina et al.2025 · 11 citationsarXiv
DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness2503.22677v2 · Ruining Li, Chuanxia Zheng, Christian Rupprecht et al.2025 · 2 citationsarXiv
Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better2503.19904v1 · Zihang Lai, Andrea Vedaldi2025 · 0 citationsarXiv
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction2503.16318v1 · Edgar Sucar, Zihang Lai, Eldar Insafutdinov et al.2025 · 9 citationsarXiv
SynCity: Training-Free Generation of 3D Worlds2503.16420v1 · Paul Engstler, Aleksandar Shtedritski, Iro Laina et al.2025 · 6 citationsarXiv
Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images2503.13439v1 · Tianhao Wu, Chuanxia Zheng, Frank Guan et al.2025 · 14 citationsarXiv
VGGT: Visual Geometry Grounded Transformer2503.11651v1 · Jianyuan Wang, Minghao Chen, Nikita Karaev et al.2025 · 479 citationsarXiv
Twinner: Shining Light on Digital Twins in a Few Snaps2503.08382v1 · Jesus Zarzar, Tom Monnier, Roman Shapovalov et al.2025 · 1 citationarXiv
Learning segmentation from point trajectories2501.12392v1 · Laurynas Karazija, Iro Laina, Christian Rupprecht et al.2025 · 4 citationsarXiv
UnCommon Objects in 3D2501.07574v1 · Xingchen Liu, Piyush Tayal, Jianyuan Wang et al.2025 · 7 citationsarXiv
PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models2412.18608v2 · Minghao Chen, Roman Shapovalov, Iro Laina et al.2024 · 22 citationsarXiv
DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction2412.04464v5 · Ben Kaye, Tomas Jakab, Shangzhe Wu et al.2024 · 2 citationsarXiv
3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes2411.14974v3 · Jan Held, Renaud Vandeghen, Abdullah Hamdi et al.2024 · 17 citationsarXiv
MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views2411.04924v1 · Yuedong Chen, Chuanxia Zheng, Haofei Xu et al.2024 · 20 citationsarXiv
CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos2410.11831v1 · Nikita Karaev, Iurii Makarov, Jianyuan Wang et al.2024 · 6 citationsarXiv
Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation2410.00890v3 · Junlin Han, Jianyuan Wang, Andrea Vedaldi et al.2024 · 0 citationsarXiv
CatFree3D: Category-agnostic 3D Object Detection with Diffusion2408.12747v1 · Wenjing Bian, Zirui Wang, Andrea Vedaldi2024 · 1 citationarXiv
3D-Aware Instance Segmentation and Tracking in Egocentric Videos2408.09860v2 · Yash Bhalgat, Vadim Tschernezki, Iro Laina et al.2024 · 5 citationsarXiv
Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics2408.04631v2 · Ruining Li, Chuanxia Zheng, Christian Rupprecht et al.2024 · 2 citationsarXiv
Career total: 369 works. 227 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.